Open AccessDevelopment of an Asset Management System Integrated with GIS and K-Means Algorithm for Large Industrial Area
Author(s) -
Ibid Athoillah,
Firda Dwi Pratiwi
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i4.1.28237
Subject(s) - it asset management , asset management , asset (computer security) , computer science , digital asset management , geospatial analysis , current asset , cluster analysis , database , geographic information system , business , finance , computer security , artificial intelligence , remote sensing , cartography , investment strategy , geology , market liquidity , geography , working capital
The large industrial area has more than a thousand assets that make asset management activities to become more challenging. However, the current asset management in several industrial companies still records the asset information in paper-based documents. Therefore, the technical problems found in current practices in the field are the difficulties in determining the actual position of assets and which group of asset belongs accurately. To overcome those problems and to improve the asset management activities, an asset management system using GIS (Geographic Information System) and K-Means Algorithm is proposed. GIS to visualize the asset coordinate and condition on a geographical map, manage and store the assets detail information and K-Means Clustering Algorithm to cluster the assets based on their coordinate and simplifies the scattered asset. The system is developed using the Waterfall model. The system is native applications built using electron framework and can be accessed within industrial area network only, to keep the user convenience and security of asset data. The Leaflet used as interactive map software frameworks to visualize the industrial map, manage the geospatial data and mapped the industrial asset, including machinery, equipment, land, and building. For the initial operation, the system contains more than 700 assets data with 6 categories and 4 clusters. This system improves the assets accuracy, reduces the time of asset management practices, and the asset clusters can be used as decision support for industrial asset management activities.